Real-time Controller Area Networks (CAN) -- managing transient surges

Authors:
Paul Richardson;Larry Sieh;Ali Elkateeb;Peter Haniak
Affiliations:
Department of Electrical and Computer Engineering, University of Michigan-Dearborn, 4901 Evergreen Rd., Dearborn, MI 48128-1491, USA. Tel.: +1 313 593 5560/ Fax: +1 313 593 9967/ E-mail: richarpc@ ...;Vetronics Technology Center (ms 265), AMSTA-TR-R, US Army Tank-Automotive RD&E/ Center, US Army TACOM, Warren, MI 48397-5000, USA. Tel.: +1 810 574 5997/ Fax: +1 810 574 5008/ E-mail: {siehl, hani ...;Department of Electrical and Computer Engineering, University of Michigan-Dearborn, 4901 Evergreen Rd., Dearborn, MI 48128-1491, USA Tel.: +1 313 593 5420/ E-mail: elkateeb@umd.umich.edu;Vetronics Technology Center (ms 265), AMSTA-TR-R, US Army Tank-Automotive RD&E/ Center, US Army TACOM, Warren, MI 48397-5000, USA. Tel.: +1 810 574 5997/ Fax: +1 810 574 5008/ E-mail: {siehl, hani ...
Venue:
Integrated Computer-Aided Engineering
Year:
2002

Citing 0
Cited 2

Stochastic and deterministic performance evaluation of automotive CAN communication

Computer Networks: The International Journal of Computer and Telecommunications Networking
Verifying worst case delays in controller area network

MMB'12/DFT'12 Proceedings of the 16th international GI/ITG conference on Measurement, Modelling, and Evaluation of Computing Systems and Dependability and Fault Tolerance

Quantified Score

Hi-index	0.00

Visualization

Abstract

Controller Area Network (CAN) is a control network protocol that can be found in a wide range of embedded systems. Control networks are inherently real-time local area networks (LANs) whose correct performance is specified in terms of the reliable and timely delivery of messages. These networks are typically required to provide long periods of uninterrupted service in harsh and dynamic environments. Under these conditions, the network is prone to transient-surges in loading that tend to upset temporal behavior. During transient-surges, it is highly desirable to sustain the timely transmission of critical messages. In this effort we describe a protocol that provides Quality of Service (QoS) support for critical real-time message transmissions under nominal conditions and during transient-surges. Our approach uses the CAN protocol in conjunction with a time-value scheduling algorithm. The QoS support for individual message transmissions considers system-state, network loading, and the value of pending messages with respect to time.